arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1303.0140cs.LGstat.ML
收藏

二阶非平稳回归在线学习

Second-Order Non-Stationary Online Learning for Regression

The Technion - Israel Institute of Technology(以色列理工学院)

Nina Vaits, Edward Moroshko, Koby Crammer

摘要:

在标准的在线学习中,学习者的目标是使累积损失与来自某个固定类的最佳性能函数相比不大得多。与离线选择的最佳函数相比,许多算法被证明具有任意接近于零的间隙。然而,许多现实世界的应用,如自适应滤波,在本质上是非平稳的,最好的预测函数可能会随着时间的推移而漂移。我们介绍了两种新的在线回归算法,旨在工作在非平稳环境。我们的第一个算法执行自适应重置忘记历史,而第二个是最后一步的最小最大最优的上下文中的漂移。我们分析了这两种算法在最坏情况下的遗憾框架,并表明,他们保持接近的最佳缓慢变化的线性函数序列的平均损失,只要累积漂移是次线性的。此外,在平稳的情况下,当没有漂移发生,我们的算法遭受对数遗憾,为以前的算法。我们的边界改善现有的,和模拟证明了这些算法的有用性相比,其他国家的最先进的方法。

英文摘要:

The goal of a learner, in standard online learning, is to have the cumulative loss not much larger compared with the best-performing function from some fixed class. Numerous algorithms were shown to have this gap arbitrarily close to zero, compared with the best function that is chosen off-line. Nevertheless, many real-world applications, such as adaptive filtering, are non-stationary in nature, and the best prediction function may drift over time. We introduce two novel algorithms for online regression, designed to work well in non-stationary environment. Our first algorithm performs adaptive resets to forget the history, while the second is last-step min-max optimal in context of a drift. We analyze both algorithms in the worst-case regret framework and show that they maintain an average loss close to that of the best slowly changing sequence of linear functions, as long as the cumulative drift is sublinear. In addition, in the stationary case, when no drift occurs, our algorithms suffer logarithmic regret, as for previous algorithms. Our bounds improve over the existing ones, and simulations demonstrate the usefulness of these algorithms compared with other state-of-the-art approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑